IMPLEMENTATION OF NAÏVE BAYES IN DETECTING HOAX NEWS

Wicaksana, Satria (2022) IMPLEMENTATION OF NAÏVE BAYES IN DETECTING HOAX NEWS. Tugas Akhir thesis, University of Technology Yogyakarta.

Text 5150411428_Satria Wicaksana.pdf Download (31kB)

Abstract

ABSTRACT Websites and blogs are well-known as news broadcast media in various fields such as news broadcasting. The validity of news articles can be valid or fake. Fake news is also known as hoax news. The purpose of making this hoax news is to persuade, manipulate, influence news readers to do things that are contrary to or prevent the right action. In this study, it is proposed to conduct a Naïve Bayes classification experiment on the detection of hoax news in English. This study uses a dataset of several news stories between valid and hoax news. In this study, the Tf-Idf calculation was used to measure the weight of a word in the hoax document and the Naïve Bayes classification method and algorithm. Naïve Bayes (NBC) to measure the probability value in a news. The Naive Bayes Classifiers method is a text classification method based on keyword probabilities in comparing training documents and test documents. The two are compared through several stages of equations, which ultimately results in the highest probability being assigned as a new document category. The results of research conducted by Naïve Bayes Classifiers researchers produced a high average accuracy, namely recall 83%, precision 83%, and accuracy 83%, and can detect the suitability of manual tagging with test news with a percentage of 85.04% Keywords: Naive, Bayes, hoax, news.

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	11 Apr 2022 04:13
Last Modified:	11 Apr 2022 04:13
URI:	http://eprints.uty.ac.id/id/eprint/9713

Actions (login required)

View Item